Back

PRATHAM

Experimenting On lea... • 1y

Tried it, seems like downgraded version of GPT 3.5, still pretty impressive. I am sure but I guess they are not using their own llm like GPT, are they using GPT's API and base for krutrim Now, imagine yourself as bhavish Agrawal. If you had all co

https://medial.app/news/bhavish-aggarwal-led-krutrim-ai-launches-its-android-app-063bc5609cfea

Nawal
•

SELF • 1y

Claude 3 Opus - GOD for now.

PRATHAM

Experimenting On lea... • 1y

Yep but sadly I haven't tried that, have you ?

ALOK MAURYA

I carry your dreams,... • 1y

I've given it a shot, and it's pretty good! But interestingly, the responses from their paid model 'Opus' and the free model 'Sonett' seem almost identical for basic tasks.

PRATHAM

Experimenting On lea... • 1y

Oh what about your opinion on opus Vs gpt 4

1 Reply

Replies (1)

ALOK MAURYA

I carry your dreams,... • 1y

I use them mostly for code generation, so based on the context I provide Opus codes work on oneshot, but I use GPT4(Using Bing Copilot) mostly as it doesn't have messaging limit

1 Reply

Recommendations from Medial

Anomaly

#Simplicity • 1y

Looking at GPT -4 what comes to your mind about chat gpt 5? Any theories then feel free to share

Account Deleted

Hey I am on Medial • 1y

Hello Guys 🤩, Claude Opus model is dominating the AI race with 86.8% by competing with GPT-4 with 256 K token processing power and GPT-4 with 138 K tokens . Rumor Is that GPT-5 will launch in August with 1 Million tokens , isn't it interesting 😲

2 Replies

Kimiko

Startups | AI | info... • 1m

✨ Claude Opus 4 = World's best coding model (72.5% on SWE-bench) ✨ Claude Sonnet 4 = Major upgrade, powering GitHub Copilot's new agent ✨ Both can think + use tools simultaneously ✨ Claude Code now GA with VS Code/JetBrains integration